Automatic 3-D segmentation of internal structures of the head in MR imagesusing a combination of similarity and free-form transformations: Part II, validation on severely atrophied brains

Studies aimed at quantifying neuroanatomical differences between population s require the volume measurements of individual brain structures, If the st udy contains a large number of images, manual segmentation is not practical . This study tests the hypothesis that a fully automatic, atlas-based segme ntation method can be used to quantify atrophy indexes derived from the bra in and cerebellum volumes in normal subjects and chronic alcoholics, This i s accomplished by registering an atlas volume with a subject volume, first using a global transformation, and then improving the registration using a local transformation. Segmented structures in the atlas volume are then map ped to the corresponding structures in the subject volume using the combine d global and local transformations. This technique has been applied to seve n normal and seven alcoholic subjects, Three magnetic resonance volumes wer e obtained for each subject and each volume was segmented automatically, us ing the atlas-based method, Accuracy was assessed by manually segmenting re gions and measuring the similarity between corresponding regions obtained a utomatically, Repeatability was determined by comparing volume measurements of segmented structures from each acquisition of the same subject. Results demonstrate that the method is accurate, that the results are repeatable, and that it can provide a method for automatic quantification of brain atro phy, even when the degree of atrophy is large.